Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and possessive pronouns used in conjunction with actions or instructions

    oai_token-act-pair · gpt-3.5-turbo

    references to personal pronouns, particularly those relating to relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arios
    -0.72
    scrib
    -0.70
    semb
    -0.68
    ãĥĩãĤ£
    -0.66
    spread
    -0.62
    Sc
    -0.62
    continental
    -0.61
    ACP
    -0.60
    hift
    -0.60
    cing
    -0.60
    POSITIVE LOGITS
     orally
    0.79
     Majesty
    0.71
     uncond
    0.70
     gently
    0.69
     majesty
    0.66
     tyr
    0.64
     onboard
    0.64
     behav
    0.62
     misunder
    0.62
     Malfoy
    0.62
    Act Density 0.168%

    No Known Activations